Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iente
    -0.31
    ientes
    -0.31
     poison
    -0.26
    ierce
    -0.25
    _ht
    -0.24
    å¤ĩ
    -0.24
    ublish
    -0.24
     flips
    -0.24
     PL
    -0.23
     Ole
    -0.23
    POSITIVE LOGITS
    ional
    0.28
    纽
    0.28
     Rudd
    0.27
    äºĴèģĶ
    0.26
    integr
    0.26
    pawn
    0.26
    forder
    0.26
     Treasury
    0.26
     Treasurer
    0.25
    èĥ¼
    0.25
    Act Density 0.012%

    No Known Activations